Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code continuations or names/topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”，
    -2.03
    ’，
    -1.64
    喜歡的
    -1.64
    悒
    -1.54
    颙
    -1.52
     baisse
    -1.52
    ，”
    -1.51
     laporan
    -1.51
     kehilangan
    -1.50
     perawatan
    -1.49
    POSITIVE LOGITS
    </strong>
    2.00
    </h3>
    1.76
     (
    1.74
    </u>
    1.66
         
    1.56
     {
    1.52
     l
    1.51
                
    1.49
    {
    1.48
     .
    1.47
    Act Density 0.001%

    No Known Activations